Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images : achieving state-of-the-art predictive performance with fewer data using Swin Transformer
© 2023 The Authors. The Journal of Pathology: Clinical Research published by The Pathological Society of Great Britain and Ireland and John Wiley & Sons Ltd..
Many artificial intelligence models have been developed to predict clinically relevant biomarkers for colorectal cancer (CRC), including microsatellite instability (MSI). However, existing deep learning networks require large training datasets, which are often hard to obtain. In this study, based on the latest Hierarchical Vision Transformer using Shifted Windows (Swin Transformer [Swin-T]), we developed an efficient workflow to predict biomarkers in CRC (MSI, hypermutation, chromosomal instability, CpG island methylator phenotype, and BRAF and TP53 mutation) that required relatively small datasets. Our Swin-T workflow substantially achieved the state-of-the-art (SOTA) predictive performance in an intra-study cross-validation experiment on the Cancer Genome Atlas colon and rectal cancer dataset (TCGA-CRC-DX). It also demonstrated excellent generalizability in cross-study external validation and delivered a SOTA area under the receiver operating characteristic curve (AUROC) of 0.90 for MSI, using the Molecular and Cellular Oncology dataset for training (N = 1,065) and the TCGA-CRC-DX (N = 462) for testing. A similar performance (AUROC = 0.91) was reported in a recent study, using ~8,000 training samples (ResNet18) on the same testing dataset. Swin-T was extremely efficient when using small training datasets and exhibited robust predictive performance with 200-500 training samples. Our findings indicate that Swin-T could be 5-10 times more efficient than existing algorithms for MSI prediction based on ResNet18 and ShuffleNet. Furthermore, the Swin-T models demonstrated their capability in accurately predicting MSI and BRAF mutation status, which could exclude and therefore reduce samples before subsequent standard testing in a cascading diagnostic workflow, in turn reducing turnaround time and costs.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:9 |
|---|---|
| Enthalten in: |
The journal of pathology. Clinical research - 9(2023), 3 vom: 01. Mai, Seite 223-235 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Guo, Bangwei [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Biomarkers |
|---|
| Anmerkungen: |
Date Completed 06.04.2023 Date Revised 14.06.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1002/cjp2.312 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM352337257 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM352337257 | ||
| 003 | DE-627 | ||
| 005 | 20231226053505.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/cjp2.312 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1174.xml |
| 035 | |a (DE-627)NLM352337257 | ||
| 035 | |a (NLM)36723384 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Guo, Bangwei |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images |b achieving state-of-the-art predictive performance with fewer data using Swin Transformer |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 06.04.2023 | ||
| 500 | |a Date Revised 14.06.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2023 The Authors. The Journal of Pathology: Clinical Research published by The Pathological Society of Great Britain and Ireland and John Wiley & Sons Ltd. | ||
| 520 | |a Many artificial intelligence models have been developed to predict clinically relevant biomarkers for colorectal cancer (CRC), including microsatellite instability (MSI). However, existing deep learning networks require large training datasets, which are often hard to obtain. In this study, based on the latest Hierarchical Vision Transformer using Shifted Windows (Swin Transformer [Swin-T]), we developed an efficient workflow to predict biomarkers in CRC (MSI, hypermutation, chromosomal instability, CpG island methylator phenotype, and BRAF and TP53 mutation) that required relatively small datasets. Our Swin-T workflow substantially achieved the state-of-the-art (SOTA) predictive performance in an intra-study cross-validation experiment on the Cancer Genome Atlas colon and rectal cancer dataset (TCGA-CRC-DX). It also demonstrated excellent generalizability in cross-study external validation and delivered a SOTA area under the receiver operating characteristic curve (AUROC) of 0.90 for MSI, using the Molecular and Cellular Oncology dataset for training (N = 1,065) and the TCGA-CRC-DX (N = 462) for testing. A similar performance (AUROC = 0.91) was reported in a recent study, using ~8,000 training samples (ResNet18) on the same testing dataset. Swin-T was extremely efficient when using small training datasets and exhibited robust predictive performance with 200-500 training samples. Our findings indicate that Swin-T could be 5-10 times more efficient than existing algorithms for MSI prediction based on ResNet18 and ShuffleNet. Furthermore, the Swin-T models demonstrated their capability in accurately predicting MSI and BRAF mutation status, which could exclude and therefore reduce samples before subsequent standard testing in a cascading diagnostic workflow, in turn reducing turnaround time and costs | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a Swin Transformer | |
| 650 | 4 | |a biomarkers | |
| 650 | 4 | |a colorectal cancer | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a digital pathology | |
| 650 | 7 | |a Proto-Oncogene Proteins B-raf |2 NLM | |
| 650 | 7 | |a EC 2.7.11.1 |2 NLM | |
| 650 | 7 | |a Biomarkers |2 NLM | |
| 700 | 1 | |a Li, Xingyu |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Miaomiao |e verfasserin |4 aut | |
| 700 | 1 | |a Jonnagaddala, Jitendra |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Hong |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Xu Steven |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The journal of pathology. Clinical research |d 2015 |g 9(2023), 3 vom: 01. Mai, Seite 223-235 |w (DE-627)NLM249745445 |x 2056-4538 |7 nnns |
| 773 | 1 | 8 | |g volume:9 |g year:2023 |g number:3 |g day:01 |g month:05 |g pages:223-235 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1002/cjp2.312 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 9 |j 2023 |e 3 |b 01 |c 05 |h 223-235 | ||